© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 50675
    Prev
    Next
    INDEX
    Explanations

    expressing thoughts and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     debunk
    -0.09
     perfection
    -0.09
    Å¡e
    -0.08
    acades
    -0.08
     Shepherd
    -0.08
    Ĥ¬
    -0.08
    nell
    -0.08
    beck
    -0.08
     Remember
    -0.08
    awan
    -0.08
    POSITIVE LOGITS
     thoughts
    0.38
     intentions
    0.31
     feelings
    0.31
     sentiments
    0.31
     Thoughts
    0.30
     desires
    0.27
     opinions
    0.25
     expressing
    0.22
     expresses
    0.22
     emotions
    0.22
    Activations Density 0.130%

    No Known Activations